Wandering pattern sensing at S-band

Xiaodong Yang, Syed Shah, Aifeng Ren, Nan Zhao, Dou Fan, Fangming Hu, Masood Ur-Rehman, Karen M. von Deneen, Jie Tian

Research output: Contribution to journalArticlepeer-review

57 Citations (Scopus)


Increasing prevalence of dementia has posed several challenges for care-givers. Patients suffering from dementia often display wandering behavior due to boredom or memory loss. It is considered to be one of the challenging conditions to manage and understand. Traits of dementia patients can compromise their safety causing serious injuries. This paper presents investigation into the design and evaluation of wandering scenarios with patients suffering from dementia using an S-band sensing technique. This frequency band is the wireless channel commonly used to monitor and characterize different scenarios including random, lapping, and pacing movements in an indoor environment. Wandering patterns are characterized depending on the received amplitude and phase information of that measures the disturbance caused in the ideal radio signal. A secondary analysis using support vector machine is used to classify the three patterns. The results show that the proposed technique carries high classification accuracy up to 90% and has good potential for healthcare applications.
Original languageEnglish
Pages (from-to)1863 - 1870
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Issue number6
Publication statusPublished - 27 Dec 2017
Externally publishedYes


  • S-Band sensing
  • wandering patterns
  • dementia


Dive into the research topics of 'Wandering pattern sensing at S-band'. Together they form a unique fingerprint.

Cite this